Mercurial Repositories > eric / file comparison
comparison: Utilities/__init__.py
Utilities/__init__.py
- branch
- 5_1_x
- changeset 1107
- cad60e83a962
- parent 882
- 34b86be88bf0
- child 1125
- 4ecd7e08246b
equal
deleted
inserted
replaced
| 1105:8a1ec3fa9d2b | 1107:cad60e83a962 |
|---|---|
| 319 index += 4 | 319 index += 4 |
| 320 else: | 320 else: |
| 321 buf += bytes(text[index], encoding="ascii") | 321 buf += bytes(text[index], encoding="ascii") |
| 322 index += 1 | 322 index += 1 |
| 323 buf = buf.replace(b"\x00", b"") | 323 buf = buf.replace(b"\x00", b"") |
| 324 return decodeBytes(buf) | |
| 325 | |
| 326 def decodeBytes(buffer): | |
| 327 """ | |
| 328 Function to decode some byte text into a string. | |
| 329 | |
| 330 @param buffer byte buffer to decode (bytes) | |
| 331 @return decoded text (string) | |
| 332 """ | |
| 333 # try UTF with BOM | |
| 334 try: | |
| 335 if buffer.startswith(BOM_UTF8): | |
| 336 # UTF-8 with BOM | |
| 337 return str(buffer[len(BOM_UTF8):], encoding='utf-8') | |
| 338 elif buffer.startswith(BOM_UTF16): | |
| 339 # UTF-16 with BOM | |
| 340 return str(buffer[len(BOM_UTF16):], encoding='utf-16') | |
| 341 elif buffer.startswith(BOM_UTF32): | |
| 342 # UTF-32 with BOM | |
| 343 return str(buffer[len(BOM_UTF32):], encoding='utf-32') | |
| 344 except (UnicodeError, LookupError): | |
| 345 pass | |
| 324 | 346 |
| 325 # try UTF-8 | 347 # try UTF-8 |
| 326 try: | 348 try: |
| 327 return str(buf, encoding="utf-8") | 349 return str(buffer, encoding="utf-8") |
| 328 except UnicodeError: | 350 except UnicodeError: |
| 329 pass | 351 pass |
| 330 | 352 |
| 331 # try codec detection | 353 # try codec detection |
| 332 try: | 354 try: |
| 333 import ThirdParty.CharDet.chardet | 355 import ThirdParty.CharDet.chardet |
| 334 guess = ThirdParty.CharDet.chardet.detect(buf) | 356 guess = ThirdParty.CharDet.chardet.detect(buffer) |
| 335 if guess and guess['encoding'] is not None: | 357 if guess and guess['encoding'] is not None: |
| 336 codec = guess['encoding'].lower() | 358 codec = guess['encoding'].lower() |
| 337 return str(buf, codec) | 359 return str(buffer, encoding=codec) |
| 338 except (UnicodeError, LookupError): | 360 except (UnicodeError, LookupError): |
| 339 pass | 361 pass |
| 340 except ImportError: | 362 except ImportError: |
| 341 pass | 363 pass |
| 342 | 364 |
| 343 return str(text, "utf-8", "ignore") | 365 return str(buffer, encoding="utf-8", errors="ignore") |
| 344 | 366 |
| 345 _escape = re.compile("[&<>\"\u0080-\uffff]") | 367 _escape = re.compile("[&<>\"\u0080-\uffff]") |
| 346 | 368 |
| 347 _escape_map = { | 369 _escape_map = { |
| 348 "&": "&", | 370 "&": "&", |
